{"id":"https://openalex.org/W4401610120","doi":"https://doi.org/10.1109/icasspw62465.2024.10627508","title":"VICMus: Variance-Invariance-Covariance Regularization for Music Representation Learning","display_name":"VICMus: Variance-Invariance-Covariance Regularization for Music Representation Learning","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4401610120","doi":"https://doi.org/10.1109/icasspw62465.2024.10627508"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10627508","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10627508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.chalmers.se/publication/542640/file/542640_Fulltext.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106529933","display_name":"Sebastian L\u00f6f","orcid":null},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Sebastian L\u00f6f","raw_affiliation_strings":["Chalmers University of Technology"],"affiliations":[{"raw_affiliation_string":"Chalmers University of Technology","institution_ids":["https://openalex.org/I66862912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059380061","display_name":"Cody Hesse","orcid":null},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Cody Hesse","raw_affiliation_strings":["Chalmers University of Technology"],"affiliations":[{"raw_affiliation_string":"Chalmers University of Technology","institution_ids":["https://openalex.org/I66862912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059966722","display_name":"Carl Thom\u00e9","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carl Thom\u00e9","raw_affiliation_strings":["Epidemic Sound"],"affiliations":[{"raw_affiliation_string":"Epidemic Sound","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059785530","display_name":"Carlos Lordelo","orcid":"https://orcid.org/0000-0002-7906-4677"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carlos Lordelo","raw_affiliation_strings":["Epidemic Sound"],"affiliations":[{"raw_affiliation_string":"Epidemic Sound","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073135559","display_name":"Jens Ahrens","orcid":"https://orcid.org/0000-0002-1706-3564"},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Jens Ahrens","raw_affiliation_strings":["Chalmers University of Technology"],"affiliations":[{"raw_affiliation_string":"Chalmers University of Technology","institution_ids":["https://openalex.org/I66862912"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5106529933"],"corresponding_institution_ids":["https://openalex.org/I66862912"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13854145,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"475","last_page":"479"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.986299991607666,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13996","display_name":"Diverse Musicological Studies","score":0.9602000117301941,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.722603440284729},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6142358183860779},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5762499570846558},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5242955088615417},{"id":"https://openalex.org/keywords/analysis-of-covariance","display_name":"Analysis of covariance","score":0.501544713973999},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4599079489707947},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4569043219089508},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4047626852989197},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.37296611070632935},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.348891019821167},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3391946256160736},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.33869075775146484}],"concepts":[{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.722603440284729},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6142358183860779},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5762499570846558},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5242955088615417},{"id":"https://openalex.org/C119340705","wikidata":"https://www.wikidata.org/wiki/Q1628597","display_name":"Analysis of covariance","level":2,"score":0.501544713973999},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4599079489707947},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4569043219089508},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4047626852989197},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.37296611070632935},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.348891019821167},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3391946256160736},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.33869075775146484},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10627508","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10627508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},{"id":"pmh:oai:research.chalmers.se:542640","is_oa":true,"landing_page_url":"https://research.chalmers.se/en/publication/28d0b553-8ec6-44fc-8259-6ef20626de0d","pdf_url":"https://research.chalmers.se/publication/542640/file/542640_Fulltext.pdf","source":{"id":"https://openalex.org/S4306402469","display_name":"Chalmers Research (Chalmers University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66862912","host_organization_name":"Chalmers University of Technology","host_organization_lineage":["https://openalex.org/I66862912"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:research.chalmers.se:542620","is_oa":false,"landing_page_url":"https://research.chalmers.se/en/publication/542620","pdf_url":null,"source":{"id":"https://openalex.org/S4306402469","display_name":"Chalmers Research (Chalmers University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66862912","host_organization_name":"Chalmers University of Technology","host_organization_lineage":["https://openalex.org/I66862912"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:research.chalmers.se:542640","is_oa":true,"landing_page_url":"https://research.chalmers.se/en/publication/28d0b553-8ec6-44fc-8259-6ef20626de0d","pdf_url":"https://research.chalmers.se/publication/542640/file/542640_Fulltext.pdf","source":{"id":"https://openalex.org/S4306402469","display_name":"Chalmers Research (Chalmers University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66862912","host_organization_name":"Chalmers University of Technology","host_organization_lineage":["https://openalex.org/I66862912"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401610120.pdf"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2593116425","https://openalex.org/W2606176153","https://openalex.org/W2963341956","https://openalex.org/W3005680577","https://openalex.org/W3093475354","https://openalex.org/W3100859887","https://openalex.org/W3134652006","https://openalex.org/W3139211892","https://openalex.org/W3162391496","https://openalex.org/W3205065023","https://openalex.org/W4221155661","https://openalex.org/W4225713393","https://openalex.org/W4286695273","https://openalex.org/W4322825062","https://openalex.org/W4372267472","https://openalex.org/W6633499030","https://openalex.org/W6678969435","https://openalex.org/W6732646663","https://openalex.org/W6736723571","https://openalex.org/W6774314701","https://openalex.org/W6779977557","https://openalex.org/W6784011672","https://openalex.org/W6791429434","https://openalex.org/W6791537541","https://openalex.org/W6791742336","https://openalex.org/W6795754764","https://openalex.org/W6802387851","https://openalex.org/W6850353053"],"related_works":["https://openalex.org/W4235479087","https://openalex.org/W1503294153","https://openalex.org/W2383820648","https://openalex.org/W2084133194","https://openalex.org/W2363838894","https://openalex.org/W2050664815","https://openalex.org/W4248848563","https://openalex.org/W4236328372","https://openalex.org/W2492984665","https://openalex.org/W4244750876"],"abstract_inverted_index":{"Recent":[0],"self-supervised":[1,132],"learning":[2],"methods":[3],"often":[4],"prevent":[5],"informational":[6],"collapse":[7],"by":[8],"implicitly":[9],"regularizing":[10],"information.":[11],"Variance-Invariance-Covariance":[12],"regularization":[13],"(VICReg)":[14],"was":[15],"introduced":[16],"as":[17],"a":[18,82,136],"non-contrastive":[19],"loss":[20],"function":[21],"that":[22,121],"explicitly":[23],"maximizes":[24],"information":[25],"through":[26],"regularization.":[27],"While":[28],"VICReg":[29,56],"has":[30],"garnered":[31],"substantial":[32],"interest":[33],"in":[34],"the":[35,43,65,88,103,128],"field":[36],"of":[37,78,116,130],"computer":[38],"vision,":[39],"its":[40],"application":[41],"to":[42],"music":[44,58,143],"domain":[45],"remains":[46],"unexplored.":[47],"To":[48],"address":[49],"this":[50],"gap,":[51],"we":[52],"introduce":[53],"VICMus":[54,63,101,123],"-":[55],"for":[57,142],"representation":[59,144],"learning.":[60,145],"We":[61,99],"pre-train":[62],"on":[64,73,87,102],"Free":[66],"Music":[67],"Archive":[68],"and":[69,111,138,148],"achieve":[70,112,127],"36.3":[71],"mAP":[72],"MagnaTagaTune,":[74],"outperforming":[75],"Contrastive":[76],"Learning":[77],"Musical":[79],"Representations":[80],"(CLMR),":[81],"recent":[83],"contrastive":[84],"method":[85],"pre-trained":[86],"ten":[89],"times":[90],"larger":[91],"Million":[92],"Song":[93],"Dataset,":[94],"which":[95],"got":[96],"35.6":[97],"mAP.":[98],"evaluate":[100],"Holistic":[104],"Audio":[105],"Representation":[106],"Evaluation":[107],"Suite":[108],"(HARES)-music":[109],"benchmark":[110],"an":[113],"average":[114],"score":[115],"51.7.":[117],"Our":[118,146],"results":[119],"indicate":[120],"while":[122],"may":[124],"not":[125],"yet":[126],"performance":[129],"state-of-the-art":[131],"models,":[133],"it":[134],"offers":[135],"promising":[137],"computationally":[139],"efficient":[140],"avenue":[141],"code":[147],"models":[149],"are":[150],"available":[151],"at":[152],"https://github.com/SebastianLoef/VICMus.":[153]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}